User Portlet
| Discussions |
|---|
| Ok, I think the response is given by the fact that Dijkstra algorithm doesnt handle negative weights and the random data generated produce negative weights sometimes. I think it would be useful if it could give a warning in next releases of... |
| Sorry, there was a mistake in the previous version of the code. The original network is calculated using euclidean distances, while the function distanceF is the one used to update the original weights. |
| Sorry, I made a mistake when copying the code example. I have edited it. |
| Thank you very much for your time and your answer. That behavior of the `DistanceMatrix` function is wild, and also the way in which the variable needs to be handled for `FindMinimum`. But yes! It works. So thank you once again for the... |
| Mathematica has different related functions to perform clustering including `ClusterClassify[]` and `FindClusters[]`. Is it possible to obtain the value of its `CriterionFunction`? As a simple example: data = ExampleData[{"MachineLearning",... |
| Thank you very much Eric! After some work, I have been able to adapt the code to my purpose. The combination of `Through[]` and `Thread[]` has been very effective. I wasn't even aware of `Through[]`. Thanks again for your time and your helpful... |
| Hi Jose, thank you again for your response! I will try to explain myself better. Having a list of cities and their populations, I have gotten a matrix of distances between them: cities = Entity["City", #] & /@ {{"Istanbul", "Istanbul", ... |
| Thank you very much for your reply! It is a simple and fast method. |
| Thanks for your reply Jim. I was aware of the Wishart distribution. However, I am not sure how can I generate a scale matrix to use that distribution. It needs to be also positive definite, and in my real case I will need around 100 variables. |
| I am using Mathematica 12.1 in Ubuntu 20.04 (Linux). It may be a bug that has been corrected in version 12.2 |